REST APIv1

REST API Reference

Direct HTTP access to Rax AI

OpenAI CompatibleJSONSSE Streaming

Overview

Base URL

All API requests use this base URL

https://ai.raxcore.dev/api/v1

OpenAI Compatible: Our API is fully compatible with OpenAI's API format. You can use existing OpenAI client libraries by changing the base URL.

JavaScript Example

api.js

// JavaScript/TypeScript fetch example
const response = await fetch('https://ai.raxcore.dev/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer rax_your_api_key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'rax-4.0',
    messages: [{ role: 'user', content: 'Hello!' }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

Python Example

api.py

# Python requests example
import requests

response = requests.post(
    'https://ai.raxcore.dev/api/v1/chat/completions',
    headers={
        'Authorization': 'Bearer rax_your_api_key',
        'Content-Type': 'application/json',
    },
    json={
        'model': 'rax-4.0',
        'messages': [{'role': 'user', 'content': 'Hello!'}],
    },
)

data = response.json()
print(data['choices'][0]['message']['content'])

Authentication

API Key Authentication

Include your API key in the Authorization header

Authorization: Bearer rax_your_api_key

Best Practices

Never expose API keys in client-side code
Store keys in environment variables
Use different keys for development and production
Rotate keys regularly

Chat Completions

POST/chat/completions

Create a chat completion

Request

Terminal

curl -X POST https://ai.raxcore.dev/api/v1/chat/completions \
  -H "Authorization: Bearer rax_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rax-4.0",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Response

response.json

{
  "id": "req_abc123def456",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "rax-4.0",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 18,
    "total_tokens": 43
  }
}

Streaming

Server-Sent Events

Stream Responses

Set stream: true to receive chunks via SSE

Request

Terminal

curl -X POST https://ai.raxcore.dev/api/v1/chat/completions \
  -H "Authorization: Bearer rax_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rax-4.0",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Stream Response Format

stream

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Each line is prefixed with data: . The stream ends with data: [DONE].

List Models

GET/models

List available models

Request

Terminal

curl https://ai.raxcore.dev/api/v1/models \
  -H "Authorization: Bearer rax_your_api_key"

Response

response.json

{
  "object": "list",
  "data": [
    {
      "id": "rax-4.0",
      "object": "model",
      "created": 1700000000,
      "owned_by": "raxcore",
      "context_window": 8192,
      "max_tokens": 4096
    },
    {
      "id": "rax-4.5",
      "object": "model",
      "created": 1700000000,
      "owned_by": "raxcore",
      "context_window": 8192,
      "max_tokens": 4096
    }
  ]
}

Usage Stats

GET/usage

Get your API usage statistics

Request

Terminal

curl https://ai.raxcore.dev/api/v1/usage \
  -H "Authorization: Bearer rax_your_api_key"

Response

response.json

{
  "object": "usage",
  "total_tokens": 150000,
  "total_requests": 1500,
  "period_start": "2024-01-01T00:00:00Z",
  "period_end": "2024-01-31T23:59:59Z",
  "breakdown": {
    "rax-4.0": {
      "tokens": 100000,
      "requests": 1000
    },
    "rax-4.5": {
      "tokens": 50000,
      "requests": 500
    }
  }
}

Request Parameters

Chat Completion Parameters

Parameters for /chat/completions endpoint

modelrequired

string

Model ID to use (rax-4.0 or rax-4.5)

messagesrequired

array

Array of message objects with role and content

temperature

number•default: 0.7

Sampling temperature (0-2)

max_tokens

number•default: 1000

Maximum tokens to generate (1-4096)

top_p

number•default: 1

Nucleus sampling threshold (0-1)

stream

boolean•default: false

Enable streaming responses

stop

array•default: null

Stop sequences to end generation

Response Format

Chat Completion Response

idstring

Unique request identifier

objectstring

Object type (chat.completion)

creatednumber

Unix timestamp

modelstring

Model used for completion

choicesarray

Array of completion choices

choices[].messageobject

Response message with role and content

choices[].finish_reasonstring

Why generation stopped (stop, length)

usageobject

Token usage statistics

Error Codes

Error Response Format

error.json

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key",
    "status": 401
  }
}

Error Codes

400bad_request

Invalid request format or parameters

401invalid_api_key

Invalid or missing API key

403forbidden

API key lacks permission for this action

429rate_limit_exceeded

Too many requests, retry after delay

500internal_error

Server error, please retry

503service_unavailable

Service temporarily unavailable

Rate Limits

Rate Limiting

Requests are limited to ensure fair usage

Free Tier

60 requests / minute

100,000 tokens / day

Pro Tier

600 requests / minute

Unlimited tokens

Rate Limit Headers: Check X-RateLimit-Remaining and X-RateLimit-Reset headers in the response to monitor your usage. When rate limited, the Retry-After header indicates wait time.

Ready to integrate?

Get your API key and start making requests today.

Get API Key Try Playground

REST APIv1

Get API Key ← All SDKs

REST API Reference

Direct HTTP access to Rax AI

OpenAI CompatibleJSONSSE Streaming

Overview

Base URL

All API requests use this base URL

https://ai.raxcore.dev/api/v1

OpenAI Compatible: Our API is fully compatible with OpenAI's API format. You can use existing OpenAI client libraries by changing the base URL.

JavaScript Example

api.js

// JavaScript/TypeScript fetch example
const response = await fetch('https://ai.raxcore.dev/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer rax_your_api_key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'rax-4.0',
    messages: [{ role: 'user', content: 'Hello!' }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

Python Example

api.py

# Python requests example
import requests

response = requests.post(
    'https://ai.raxcore.dev/api/v1/chat/completions',
    headers={
        'Authorization': 'Bearer rax_your_api_key',
        'Content-Type': 'application/json',
    },
    json={
        'model': 'rax-4.0',
        'messages': [{'role': 'user', 'content': 'Hello!'}],
    },
)

data = response.json()
print(data['choices'][0]['message']['content'])

Authentication

API Key Authentication

Include your API key in the Authorization header

Authorization: Bearer rax_your_api_key

Best Practices

Never expose API keys in client-side code
Store keys in environment variables
Use different keys for development and production
Rotate keys regularly

Chat Completions

POST/chat/completions

Create a chat completion

Request

Terminal

curl -X POST https://ai.raxcore.dev/api/v1/chat/completions \
  -H "Authorization: Bearer rax_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rax-4.0",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Response

response.json

{
  "id": "req_abc123def456",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "rax-4.0",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 18,
    "total_tokens": 43
  }
}

Streaming

Server-Sent Events

Stream Responses

Set stream: true to receive chunks via SSE

Request

Terminal

curl -X POST https://ai.raxcore.dev/api/v1/chat/completions \
  -H "Authorization: Bearer rax_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rax-4.0",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Stream Response Format

stream

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"req_abc123","object":"chat.completion.chunk","created":1700000000,"model":"rax-4.0","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Each line is prefixed with data: . The stream ends with data: [DONE].

List Models

GET/models

List available models

Request

Terminal

curl https://ai.raxcore.dev/api/v1/models \
  -H "Authorization: Bearer rax_your_api_key"

Response

response.json

{
  "object": "list",
  "data": [
    {
      "id": "rax-4.0",
      "object": "model",
      "created": 1700000000,
      "owned_by": "raxcore",
      "context_window": 8192,
      "max_tokens": 4096
    },
    {
      "id": "rax-4.5",
      "object": "model",
      "created": 1700000000,
      "owned_by": "raxcore",
      "context_window": 8192,
      "max_tokens": 4096
    }
  ]
}

Usage Stats

GET/usage

Get your API usage statistics

Request

Terminal

curl https://ai.raxcore.dev/api/v1/usage \
  -H "Authorization: Bearer rax_your_api_key"

Response

response.json

{
  "object": "usage",
  "total_tokens": 150000,
  "total_requests": 1500,
  "period_start": "2024-01-01T00:00:00Z",
  "period_end": "2024-01-31T23:59:59Z",
  "breakdown": {
    "rax-4.0": {
      "tokens": 100000,
      "requests": 1000
    },
    "rax-4.5": {
      "tokens": 50000,
      "requests": 500
    }
  }
}

Request Parameters

Chat Completion Parameters

Parameters for /chat/completions endpoint

modelrequired

string

Model ID to use (rax-4.0 or rax-4.5)

messagesrequired

array

Array of message objects with role and content

temperature

number•default: 0.7

Sampling temperature (0-2)

max_tokens

number•default: 1000

Maximum tokens to generate (1-4096)

top_p

number•default: 1

Nucleus sampling threshold (0-1)

stream

boolean•default: false

Enable streaming responses

stop

array•default: null

Stop sequences to end generation

Response Format

Chat Completion Response

idstring

Unique request identifier

objectstring

Object type (chat.completion)

creatednumber

Unix timestamp

modelstring

Model used for completion

choicesarray

Array of completion choices

choices[].messageobject

Response message with role and content

choices[].finish_reasonstring

Why generation stopped (stop, length)

usageobject

Token usage statistics

Error Codes

Error Response Format

error.json

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key",
    "status": 401
  }
}

Error Codes

400bad_request

Invalid request format or parameters

401invalid_api_key

Invalid or missing API key

403forbidden

API key lacks permission for this action

429rate_limit_exceeded

Too many requests, retry after delay

500internal_error

Server error, please retry

503service_unavailable

Service temporarily unavailable

Rate Limits

Rate Limiting

Requests are limited to ensure fair usage

Free Tier

60 requests / minute

100,000 tokens / day

Pro Tier

600 requests / minute

Unlimited tokens

Rate Limit Headers: Check X-RateLimit-Remaining and X-RateLimit-Reset headers in the response to monitor your usage. When rate limited, the Retry-After header indicates wait time.

Ready to integrate?

Get your API key and start making requests today.

Get API Key Try Playground